ARPEGE Cloud Cover Forecast Postprocessing with Convolutional Neural Network

Florian Dupuy, Olivier Mestre, Mathieu Serrurier, Valentín Kivachuk Burdá, Michaël Zamo, Naty Citlali Cabrera-Gutiérrez, Mohamed Chafik Bakkay, Jean‐Christophe Jouhaud et al.

Weather and Forecasting 2020 article cited by 40

Source Open-access PDF More in Climate & Environment

importance 4/10 partially solved Meteorological Phenomena and Simulations weather forecasting stage: research

Problem

Numerical weather prediction models have significant biases in cloud cover forecasts, a hard-to-forecast variable needed for planning land observation missions from space.

Why it matters

Cloud cover forecasts are crucial for planning space-based land observation missions.

What the AI did

A U-Net convolutional neural network postprocessed ARPEGE cloud cover forecasts using spatial fields of NWP predictors, trained against satellite-derived gridded cloud cover over Europe.

Results

Significant improvements over Europe; U-Net outperforms traditional machine learning methods; no numeric metrics in abstract.

Impact

Peer-reviewed demonstration that CNN postprocessing improves cloud cover forecasts over Europe.

Record

Venue	Weather and Forecasting
Published	2020
Work type	article
Authors	Florian Dupuy, Olivier Mestre, Mathieu Serrurier, Valentín Kivachuk Burdá, Michaël Zamo, Naty Citlali Cabrera-Gutiérrez, Mohamed Chafik Bakkay, Jean‐Christophe Jouhaud et al.
Citations	40 (OpenAlex, at import time)
References	33
Model or method	U-Net (CNN)
Organization	Météo-France (ARPEGE model owner)
Primary source	https://doi.org/10.1175/waf-d-20-0093.1
Open access	hybrid
Keywords	cloud cover, postprocessing, U-Net, CNN, NWP, weather forecasting

Importance rating

4 / 10

real but narrower advance

Abstract calls cloud cover crucial for applications like planning land observation missions from space; a real but fairly narrow operational advance with no stated scale.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Climate & Environment

#	Paper	Year	Citations	Importance
1	Learning skillful medium-range global weather forecasting Rémi Lam, Álvaro Sánchez‐González, Matthew Willson, Peter Wirnsberger,...	2023	1,416	8
2	Accurate medium-range global weather forecasting with 3D neural networks Kaifeng Bi, Lingxi Xie, Hengheng Zhang, Xin Chen, Xiaotao Gu, Qi Chuan...	2023	1,631	8
3	FuXi: a cascade machine learning forecasting system for 15-day global weather forecast Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Qi Yuan,...	2023	355	8
4	Skilful nowcasting of extreme precipitation with NowcastNet Yuchen Zhang, Mingsheng Long, Kaiyuan Chen, Lanxiang Xing, Ronghua Jin...	2023	451	8
5	Forecasting Renewable Energy Generation with Machine Learning and Deep Learning: Current Advances and Future Prospects Natei Ermias Benti, Mesfin Diro Chaka, Addisu Gezahegn Semie	2023	378	8